In [32]:
#creating histograms of three interested subject to have a proper look at their distribution
math_bins=np.arange(50,df_pisa_clean['MATH'].max()+10,10)
reading_bins=np.arange(5,df_pisa_clean['READING'].max()+10,10)
science_bins=np.arange(20,df_pisa_clean['SCIENCE'].max()+10,10)
plt.figure(figsize=(30,8))
plt.subplot(1, 3, 1)
plt.hist(df_pisa_clean['MATH'],bins=math_bins);
plt.title('Maths Average',fontsize=30)
plt.axvline(df_pisa_clean['MATH'].mean(), color='r', linestyle='--', label='mean')
plt.text(df_pisa_clean['MATH'].mean(), 0.01, f"mean: {df_pisa_clean['MATH'].mean():.2f}", ha='left', va = 'bottom', color='r')
plt.legend()
plt.subplot(1, 3, 2)
plt.hist(df_pisa_clean['SCIENCE'],bins=science_bins);
plt.title('Science Average',fontsize=30)
plt.axvline(df_pisa_clean['SCIENCE'].mean(), color='r', linestyle='--', label='mean')
plt.text(df_pisa_clean['SCIENCE'].mean(), 0.01, f"mean: {df_pisa_clean['SCIENCE'].mean():.2f}", ha='left', va = 'bottom', color='r')
plt.legend()
plt.subplot(1, 3, 3)
plt.hist(df_pisa_clean['READING'],bins=reading_bins);
plt.title('Reading Average',fontsize=30)
plt.axvline(df_pisa_clean['READING'].mean(), color='r', linestyle='--', label='mean')
plt.text(df_pisa_clean['READING'].mean(), 0.01, f"mean: {df_pisa_clean['READING'].mean():.2f}", ha='left', va = 'bottom', color='r')
plt.legend()
Out[32]:
<matplotlib.legend.Legend at 0x1cb5897c490>
